Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or distinctions between multiple items or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contrasting different things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.66
    Бахар
    -0.59
    webElementXpaths
    -0.55
    isContained
    -0.54
    MockMvc
    -0.52
    parsedMessage
    -0.50
    Enllaces
    -0.49
     pinulongan
    -0.47
     yyr
    -0.47
    NOPQRST
    -0.46
    POSITIVE LOGITS
    Unlike
    0.46
     églises
    0.42
     Unlike
    0.41
    HandlerContext
    0.40
    ⓘ
    0.38
    unlike
    0.38
     Allociné
    0.37
     unlike
    0.37
    libatkan
    0.36
     Bíblia
    0.36
    Act Density 0.043%

    No Known Activations